Qatar Construction Surge Capacity Forecaster
Qatar's construction sector is poised for a 6.7% surge driven by strategic investment projects. Build a Python demand forecasting agent that processes tender announcements, raw material import statistics, and labor capacity indices to predict supply bottlenecks. Achieve accurate forecasts with under 4% mean absolute percentage error.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop an predictive analytics agent in Python to forecast supply chain bottlenecks across Qatar's expanding construction sector.
How work is evaluated
Evaluates demand forecast accuracy against benchmark material requirements.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
growth_scaling_check
Ensures forecast accounts for reported 6.7% sector surge
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
mape_score
Mean Absolute Percentage Error relative to ground truth demand • target: 3.8 • range: 0-100
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Aggregate sector-wide construction tender values and material volume metrics.
Apply time-series demand forecasting models (ARIMA / Prophet / XGBoost).
Identify material shortfalls (rebar, cement, aggregate) in advance.
Generate early warning dashboards for procurement officers.
Reference links and supporting material
Historical macro-construction data and tender pipelines from Qatar infrastructure authorities.
Challenge setup
Evaluates demand forecast accuracy against benchmark material requirements.
Challenge input
JSON containing quarterly growth rate, tender pipeline value, and baseline demand
Python Data Stack
Provides numerical modeling and time-series logic.
Evaluated output
JSON with predicted rebar demand, shortfall risk level, and confidence interval
- Ensures forecast accounts for reported 6.7% sector surge
- Mean Absolute Percentage Error relative to ground truth demand • target: 3.8 • range: 0-100
- Benchmark: DemandForecastBench
- Mape Score target: 3.8
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
- deepchecks · Required
- Fiddler AI · Optional
- LiveKit · Optional
Evaluation contract
- growth_scaling_check · Weight 1
- mape_score · Weight 1
Metrics
- mape_score · Target 3.8
Benchmarks
- DemandForecastBench
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON containing quarterly growth rate, tender pipeline value, and baseline demand
Output: JSON with predicted rebar demand, shortfall risk level, and confidence interval
Execution harness: Python
Evaluation tools
- Python Data Stack · Forecasting Framework
Recipe freeze marker
No recipe freeze time is recorded.